github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-07-07 21:42:08 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions
1335 commits 3 branches 2 tags 866 MiB
Commit graph

1335 commits

This branch
This branch
All branches
Author SHA1 Message Date
leno3003
5267017f7d added sumbmodules 2022-03-30 15:05:22 +02:00
leno3003
774932a5b0 added sumbmodules 2022-03-30 14:44:24 +02:00
leno3003
c3aad6a59b added sumbmodules 2022-03-30 14:44:14 +02:00
leno3003
a0ecfc063b added sumbmodules 2022-03-30 14:33:37 +02:00
leno3003
d415f56135 added sumbmodules 2022-03-30 14:32:47 +02:00
leno3003
25f93f313f added sumbmodules 2022-03-30 14:30:08 +02:00
leno3003
a900a1f02f added sumbmodules 2022-03-30 14:15:01 +02:00
leno3003
6d68692e74 added sumbmodules 2022-03-30 14:10:30 +02:00
leno3003
d4279606f4 added sumbmodules 2022-03-30 14:04:21 +02:00
leno3003
887286edc5 added sumbmodules 2022-03-30 12:49:01 +02:00
leno3003
dc39e72fb9 added sumbmodules 2022-03-30 12:33:35 +02:00
leno3003
05850a227c check if pkl exist to apply modifications 2022-03-29 21:23:29 +02:00
leno3003
2995a07f0e check if pkl exist to apply modifications 2022-03-29 19:06:47 +02:00
leno3003
5918800f14 check if pkl exist to apply modifications 2022-03-29 19:05:55 +02:00
leno3003
788e49b82c check if pkl exist to apply modifications 2022-03-29 18:21:33 +02:00
leno3003
b9162dfe48 check if pkl exist to apply modifications 2022-03-29 18:16:38 +02:00
leno3003
a2b8f3c5a2 check if pkl exist to apply modifications 2022-03-29 14:25:05 +02:00
leno3003
3dc9366d18 check if pkl exist to apply modifications 2022-03-29 14:12:12 +02:00
leno3003
230d7df17e check if pkl exist to apply modifications 2022-03-29 14:09:54 +02:00
leno3003
a14bb4ae86 check if pkl exist to apply modifications 2022-03-29 13:10:53 +02:00
leno3003
5b04cc047e check if pkl exist to apply modifications 2022-03-29 13:07:07 +02:00
leno3003
b3134a99d0 automatized arguments with pickle 2022-03-29 12:26:54 +02:00
leno3003
d132667138 automatized arguments with pickle 2022-03-29 09:23:26 +02:00
leno3003
dee168e5a6 automatized arguments with pickle 2022-03-28 22:43:24 +02:00
leno3003
afd87df67a automatized arguments with pickle 2022-03-28 18:30:15 +02:00
leno3003
9f30b24459 automatized arguments with pickle 2022-03-28 17:13:28 +02:00
leno3003
401030b7b0 automatized arguments with pickle 2022-03-28 17:13:14 +02:00
leno3003
21024c64ad automatized arguments with pickle 2022-03-28 17:03:36 +02:00
leno3003
05ebcfdef2 automatized arguments with pickle 2022-03-28 16:21:54 +02:00
leno3003
e09e1f166d automatized arguments with pickle 2022-03-28 16:18:15 +02:00
leno3003
a5fad7d8d5 automatized arguments with pickle 2022-03-28 16:16:45 +02:00
leno3003
688b3e1567 automatized arguments with pickle 2022-03-28 15:54:06 +02:00
iperov
9704c5d8f8 additional download link 2022-03-03 21:35:25 +04:00
iperov
8c79e70191 fix broken torrent link 2022-01-03 12:20:51 +04:00
iperov
292b562eb7 upd link 2021-11-21 04:39:12 +04:00
iperov
9b331e59dd upd link 2021-11-21 04:38:30 +04:00
iperov
1badaa4b4c fix 2021-11-20 16:08:41 +04:00
iperov
388964e8d0 fix model export. Update tf2onnx to 1.9.2 2021-11-20 16:05:44 +04:00
iperov
4b6bf003b8 Merger: fix rct color transfer 2021-11-13 13:33:01 +04:00
iperov
ce624735c0 README: added more tiktok accounts 2021-11-06 22:55:51 +04:00
iperov
7326771c02 fixed rct color transfer function, incorrectly clip colors before 2021-10-23 09:53:40 +04:00
iperov
1aa9463edf update windows magnet link 2021-10-20 19:02:20 +04:00
iperov
853312e84c fix 2021-10-18 13:18:59 +04:00
iperov
71f22957a6 SAEHD: random scale increased to -0.15+0.15. Improved lr_dropout capability to reach lower value of the loss. 
When random_warp is off, inter_AB network is no longer trained to keep the face more src-like.

added option Random hue/saturation/light intensity applied to the src face set only at the input of the neural network. Stabilizes color perturbations during face swapping. Reduces the quality of the color transfer by selecting the closest one in the src faceset. Thus the src faceset must be diverse enough. Typical fine value is 0.05.

AMP: random scale increased to -0.15+0.15. Improved lr_dropout capability to reach lower value of the loss.
 2021-10-18 11:03:23 +04:00
iperov
f71a9e6bbd update SampleProcessor.py 2021-10-18 11:02:54 +04:00
iperov
a1ba64be10 _ 2021-10-18 10:51:25 +04:00
iperov
14cc9d4e5f _ 2021-10-17 21:37:22 +04:00
iperov
d8c7cc3d93 DFLJPG increase max chunk size for xseg data 2021-10-13 14:35:26 +04:00
iperov
f64b2495d9 dev_misc: code to extract microsoft/FaceSynthetics dataset 2021-10-12 17:23:57 +04:00
iperov
f48e852de3 SAEHD: better training for bg_style_power 2021-10-12 15:17:41 +04:00